Work

Stacking dependency parsers

Year: 2008

Type: conference-paper

Abstract: We explore a stacked framework for learning to predict dependency structures for natural language sentences. A typical approach in graph-based dependency parsing has been to assume a factorized model, where local features are used but a global function is optimized (McDonald et al., 2005b). Recently Nivre and McDonald (2008) used the output of one dependency parser to provide features for another. We show that this is an example of stacked learning, in which a second predictor is trained to improve the performance of the first. Further, we argue that this technique is a novel way of approximating rich non-local features in the second parser, without sacrificing efficient, model-optimal prediction. Experiments on twelve languages show that stacking transition-based and graph-based parsers improves performance over existing state-of-the-art dependency parsers.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.3115/1613715.1613738

Authors: André F. T. Martins, Dipanjan Das, Noah A. Smith, Eric P. Xing

Institutions: Instituto de Telecomunicações, Instituto Superior Técnico, Carnegie Mellon University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Science Foundation, Carnegie Mellon Portugal, Fundação para a Ciência e a Tecnologia, Division of Biological Infrastructure

Awards: III-COR+RI: Novel Statistical Models and Algorithms for Network Modeling, Mining and Reverse Engineering, Indexing, Mining and Modeling Spatio-Temporal Patterns of Gene Expressions, CAREER: Novel Statistical Models and Computational Algorithms for Evolutionary Genomics, RI: Parsing Models and Algorithms for Morphologically Rich Languages, G7042103515